6 citations · 14 across the 33 of their papers we have counts for
39 papers · 1 filter
SM4RT: Learning Structured Motion Geometry for 4D Reconstruction
Shing Ho J. Lin, Wenzhao Zheng, Dong Zhuo +3
Geometry Foundation Models (GFMs) have substantially advanced monocular 3D reconstruction, yet extending this capability to 4D dynamic understanding remains a fundamental challenge…
IBRSteG: Learning a Generalizable Steganography Framework for 3D Gaussian Splatting
Fanye Kong, Hongyu Xia, Yu Zheng +3
Recent advances in deep learning have notably improved steganographic message hiding. However, designing a generalizable steganographic approach for 3D Gaussian Splatting (3DGS) th…
IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation
Yuqi Wu, Tianyu Hu, Wenzhao Zheng +4
Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing visual geometry foundat…
Vega: Learning to Drive with Natural Language Instructions
Sicheng Zuo, Yuxuan Li, Wenzhao Zheng +3
Vision-language-action models have reshaped autonomous driving to incorporate languages into the decision-making process. However, most existing pipelines only utilize the language…
DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and Understanding
Dong Zhuo, Wenzhao Zheng, Sicheng Zuo +4
With the growing adoption of vision-language-action models and world models in autonomous driving systems, scalable image tokenization becomes crucial as the interface for the visu…
Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation
Weijia Dou, Wenzhao Zheng, Weiliang Chen +3
Recent generative models can produce high-fidelity videos, yet they often exhibit 3D spatial geometric inconsistencies. Existing evaluation methods fail to accurately characterize…
Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
Jianghao Yin, Qin Chen, Kedi Chen +3
Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation…
Astra: General Interactive World Model with Autoregressive Denoising
Yixuan Zhu, Jiaqi Feng, Wenzhao Zheng +5
Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability t…
Moaw: Unleashing Motion Awareness for Video Diffusion Models
Tianqi Zhang, Ziyi Wang, Wenzhao Zheng +5
Video diffusion models, trained on large-scale datasets, naturally capture correspondences of shared features across frames. Recent works have exploited this property for tasks suc…
SFTok: Bridging the Performance Gap in Discrete Tokenizers
Qihang Rao, Borui Zhang, Wenzhao Zheng +2
Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations…
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
Minglei Shi, Haolin Wang, Borui Zhang +11
Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generati…
NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localization
Yifei Li, Haoyuan He, Yu Zheng +5
The accessibility surge and abuse risks of user-friendly image editing models have created an urgent need for generalizable, up-to-date methods for Image Manipulation Detection and…
Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning
Yifei Li, Wenzhao Zheng, Yanran Zhang +5
The misuse of AI-driven video generation technologies has raised serious social concerns, highlighting the urgent need for reliable AI-generated video detectors. However, most exis…
Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation
Yanran Zhang, Ziyi Wang, Wenzhao Zheng +3
Generating interactive and dynamic 4D scenes from a single static image remains a core challenge. Most existing generate-then-reconstruct and reconstruct-then-generate methods deco…
Terra: Explorable Native 3D World Model with Point Latents
Yuanhui Huang, Weiliang Chen, Wenzhao Zheng +4
World models have garnered increasing attention for comprehensive modeling of the real world. However, most existing methods still rely on pixel-aligned representations as the basi…
QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection
Yanran Zhang, Bingyao Yu, Yu Zheng +5
The emergence of visual autoregressive (AR) models has revolutionized image generation while presenting new challenges for synthetic image detection. Unlike previous GAN or diffusi…
Latent Diffusion Model without Variational Autoencoder
Minglei Shi, Haolin Wang, Wenzhao Zheng +6
Recent progress in diffusion-based visual generation has largely relied on latent diffusion models with variational autoencoders (VAEs). While effective for high-fidelity synthesis…
Quantize-then-Rectify: Efficient VQ-VAE Training
Borui Zhang, Qihang Rao, Wenzhao Zheng +2
Visual tokenizers are pivotal in multimodal large models, acting as bridges between continuous inputs and discrete tokens. Nevertheless, training high-compression-rate VQ-VAEs rema…
Streaming 4D Visual Geometry Transformer
Dong Zhuo, Wenzhao Zheng, Jiahe Guo +3
Perceiving and reconstructing 3D geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and low-latency applications, we propose a st…
Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory
Yuqi Wu, Wenzhao Zheng, Jie Zhou +1
Dense 3D scene reconstruction from an ordered sequence or unordered image collections is a critical step when bringing research in computer vision into practical scenarios. Followi…
Learning Counterfactually Decoupled Attention for Open-World Model Attribution
Yu Zheng, Boyang Gong, Fanye Kong +6
In this paper, we propose a Counterfactually Decoupled Attention Learning (CDAL) method for open-world model attribution. Existing methods rely on handcrafted design of region part…
GenWorld: Towards Detecting AI-generated Real-world Simulation Videos
Weiliang Chen, Wenzhao Zheng, Yu Zheng +4
The flourishing of video generation technologies has endangered the credibility of real-world information and intensified the demand for AI-generated video detectors. Despite some…
SpectralAR: Spectral Autoregressive Visual Generation
Yuanhui Huang, Weiliang Chen, Wenzhao Zheng +3
Autoregressive visual generation has garnered increasing attention due to its scalability and compatibility with other modalities compared with diffusion models. Most existing meth…
OGGSplat: Open Gaussian Growing for Generalizable Reconstruction with Expanded Field-of-View
Yanbo Wang, Ziyi Wang, Wenzhao Zheng +2
Reconstructing semantic-aware 3D scenes from sparse views is a challenging yet essential research direction, driven by the demands of emerging applications such as virtual reality…